stitch-code-to-design

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The required workflow instructs running stitch-extract-static-html and stitch-extract-design-md on the target app/source tree, which at runtime can ingest outsider-authored free text from the target web app/static pages or downloaded source content into the agent’s LLM context for processing.